[Preprint] UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution, 2021

Arbitrary-scale super-resolution is a raising research topic with tremendous application potentials. Prior CNN-based SR approaches usually apply to only one fixed resolution scale, and thus unable to adjust their output dimension without changing the low-resolution input. Such design creates a huge gap between academic research and practical usage, and a majority of image up-sampling applications, even sensitive to precision, still heavily relied on bicubic interpolation despite its poor quality.

Related Repos



pfnet-research Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th place solution
 

WeikaiTan A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways
 

seungeunrho The exact codes used by the team "liveinparis" at the kaggle football competition ranked 8th/1141
 

microsoft FLAML is a Python library designed to automatically produce accurate machine learning models with low computational cost. It frees users from selecting learners and hyperparameters for each learner.
 

aimagelab An Extendible (General) Continual Learning Framework based on Pytorch.
 

bismex This is a repository for organizing articles related to cross-modality person re-identification (especially focusing on visible-thermal person reid). Most papers are linked to the pdf address provided by "arXiv" or "Openaccess".
 

zhiqwang Yet another yolov5, with its runtime stack for libtorch, onnx and specialized accelerators. You like torchvision's retinanet? You like yolov5? You love yolov5rt!
 

google-research Attribution is one tool in the interpretability toolkit that provides ranked importance values on an input (x) in relation to an output (y).